VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator
Open accessThe DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index.
Abstract
One camera and one low-cost inertial measurement unit (IMU) form a monocular visual-inertial system (VINS), which is the minimum sensor suite (in size, weight, and power) for the metric six degrees-of-freedom (DOF) state estimation. In this paper, we present VINS-Mono: a robust and versatile monocular visual-inertial state estimator. Our approach starts with a robust procedure for estimator initialization. A tightly coupled, nonlinear optimization-based method is used to obtain highly accurate visual-inertial odometry by fusing preintegrated IMU measurements and feature observations. A loop detection module, in combination with our tightly coupled formulation, enables relocalization with minimum computation. We additionally perform 4-DOF pose graph optimization to enforce the global consistency. Furthermore, the proposed system can reuse a map by saving and loading it in an efficient way. The current and previous maps can be merged together by the global pose graph optimization. We validate the performance of our system on public datasets and real-world experiments and compare against other state-of-the-art algorithms. We also perform an onboard closed-loop autonomous flight on the microaerial-vehicle platform and port the algorithm to an iOS-based demonstration. We highlight that the proposed work is a reliable, complete, and versatile system that is applicable for different applications that require high accuracy in localization. We open source our implementations for both PCs (https://github.com/HKUST-Aerial-Robotics/VINS-Mono) and iOS mobile devices (https://github.com/HKUST-Aerial-Robotics/VINS-Mobile).
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In terms of vision-IMU-GPS fusion, VINS-Fusion has become a mainstream solution for large-scale, high-precision localization and is widely used in UAVs and mobile robots.”
From Multimodal fusion and vision–language models: A survey for robot vision (2026) · cites this paper as [151]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Multiple View Geometry in Computer Vision
Hartley, R., & Zisserman, A. (2004) · doi:10.1017/cbo9780511811685 · Cited by 21,070
Are we ready for autonomous driving? The KITTI vision benchmark suite
Geiger, A., Lenz, P., & Urtasun, R. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248074 · Cited by 14,897 · cited 3×
“Relative pose error [42] in MH_05_difficult.”
MethodInfluential(1981) · Cited by 11,963
Shi, J., & Tomasi (1994) · Proceedings of IEEE Conference on Computer Vision and Pattern Recognition CVPR-94 · doi:10.1109/cvpr.1994.323794 · Cited by 7,724 · cited 1×
“features are detected [32] to maintain a minimum number (100– 300) of features in each image.”
BackgroundRobust estimation of a location parameter
Huber, P. J. (1964) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177703732 · Cited by 7,228
ORB-SLAM: A Versatile and Accurate Monocular SLAM System
Mur-Artal, R., Montiel, J. M. M., & Tardos, J. D. (2015) · IEEE Transactions on Robotics · doi:10.1109/tro.2015.2463671 · Cited by 6,778 · cited 7×
“ORB-SLAM [4] is able to close loops and reuse the map, which takes advantage of Bag-of-World [6].”
BackgroundMethodInfluentialParallel Tracking and Mapping for Small AR Workspaces
Klein, G., & Murray, D. (2007) · 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality · doi:10.1109/ismar.2007.4538852 · Cited by 4,346
Bundle Adjustment — A Modern Synthesis
Triggs, B., McLauchlan, P. F., Hartley, R. I., & Fitzgibbon, A. W. (2000) · Lecture Notes in Computer Science · doi:10.1007/3-540-44480-7_21 · Cited by 3,988 · cited 1×
“Finally, a global full bundle adjustment [36] is applied to minimize the total reprojection error of all feature observations.”
MethodA benchmark for the evaluation of RGB-D SLAM systems
Sturm, J., Engelhard, N., Endres, F., Burgard, W., & Cremers, D. (2012) · 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2012.6385773 · Cited by 3,976 · cited 3×
“TABLE I RMSE [43] IN EUROC DATASETS IN METERS”
BackgroundMethodInfluentialLSD-SLAM: Large-scale direct monocular SLAM
Engel, J., Schöps, T., & Cremers, D. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10605-2_54 · Cited by 3,851 · cited 3×
“Noticeable approaches include PTAM [1], SVO [2], LSD-SLAM [3], DSO [5], and ORB-SLAM [4].”
BackgroundMethod
Cited by
Items 701–800 of 1,001
ARDEA—An MAV with skills for future planetary missions
Lutz, P., Muller, M. G., Maier, M., Stoneman, S., Tomić, T., von Bargen, I., Schuster, M. J., Steidle, F., Wedler, A., Stürzl, W., et al. (2020) · Journal of Field Robotics · doi:10.1002/rob.21949 · Cited by 38
“Most visual‐inertial odometries (VIOs) for MAVs use an IMU in combination with a single camera (Bloesch, Omari, Hutter, & Siegwart, 2015; Leutenegger, Lynen, Bosse, Siegwart, & Furgale, 2015; Mourikis & Roumeliotis, 2007; Qin, Li, & Shen, 2018).”
Fisher Information Field: an Efficient and Differentiable Map for Perception-aware PlanningPreprint
Zhang, Z., & Scaramuzza, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.03324 · Cited by 44
“From a practical perspective, when a robot operates in a (partially) known environment, visual localization is often used to bound the drift accumulated in local motion estimation such as visual-inertial odometry (VIO) [9], [10].”
BackgroundMonocular Visual-Inertial Odometry with Planar Regularities
Chen, C., Geneva, P., Peng, Y., Lee, W., & Huang, G. P. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160620 · Cited by 40
“This plane detection method was extended to include lines within the monocular VINS-Mono [7] framework in PLP-VIO [56], which additionally enforced point-to-line and line-to-plane regularities.”
MethodSun, Y., Wang, Q., Yan, C., Feng, Y., Tan, R., Shi, X., & Wang, X. (2023) · Remote Sensing · doi:10.3390/rs15153881 · Cited by 32
Unsupervised Monocular Depth Estimation for Monocular Visual SLAM Systems
Liu, F., Huang, M., Ge, H., Tao, D., & Gao, R. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3342210 · Cited by 37
“Some representative VIO methods exist that leverage filters or optimization frameworks to improve tracking accuracy, such as SSF [28], MSCKF [29], Falquez [30], and VINS-Mono [31].”
MethodA Survey on Monocular Re-Localization: From the Perspective of Scene Map Representation
Miao, J., Jiang, K., Wen, T., Wang, Y., Jia, P., Wijaya, B., Zhao, X., Qian, C., Xiao, Z., Huang, J. H., et al. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2024.3378716 · Cited by 54
“For the same purpose, recent advances in HD-MRL begin to integrate relative pose constraint by visual feature tracking in VO[192]andvisual(-inertial)SLAM[101],[129]sothattracked visualfeaturescanbeconsideredascomplementarylocalization informationtotheHDmapelements.”
Advancements in perception system with multi-sensor fusion for embodied agents
Du, H., Ren, L., Wang, Y., Cao, X. S., & Sun, C. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102859 · Cited by 37
M2CS: A Multimodal and Campus‐Scapes Dataset for Dynamic SLAM and Moving Object Perception
Zhao, H., Yao, M., Zhao, Y., Jiang, Y., Zhang, H., Xiao, X., & Gao, K. (2024) · Journal of Field Robotics · doi:10.1002/rob.22468 · Cited by 37
Alamdari, A. G., Zade, F. A., & Ebrahimkhanlou, A. (2025) · Sensors · doi:10.3390/s25030712 · Cited by 37
Optimal Trajectory Generation for Quadrotor Teach-and-Repeat
Gao, F., Wang, L., Wang, K., Wu, W., Zhou, B., Han, L., & Shen, S. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2895110 · Cited by 31
“[20] T. Qin, P. Li, and S. Shen, “VINS-MONO: A robust and versatile monocular visual-inertial state estimator,” IEEE Trans.”
BackgroundMethodInfluentialSelf-citationDirect Visual-Inertial Ego-Motion Estimation Via Iterated Extended Kalman Filter
Zhong, S., & Chirarattananon, P. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2968071 · Cited by 28
“In Section IV, extensive flight experiments were performed to evaluate and benchmark the performance of the proposed method with respect to two state-of-the-art VINS [2], [16].”
BackgroundMethodInfluentialBidirectional Trajectory Computation for Odometer-Aided Visual-Inertial SLAM
Liu, J., Gao, W., & Hu, Z. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3059564 · Cited by 28
“The criterion to judge whether an image frame is a keyframe is the same as that in [14].”
BackgroundMethodSLAMANTIC - Leveraging Semantics to Improve VSLAM in Dynamic Environments
Schörghuber, M., Steininger, D., Cabon, Y., Humenberger, M., & Gelautz, M. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00468 · Cited by 37
“To reduce drift and to directly recover scale, some methods integrate inertial measurements [4, 16], [23, 22] or utilize learning-based techniques [29, 30, 18].”
MethodLi, D., Yang, W., Shi, X., Guo, D., Long, Q., Qiao, F., & Wei, Q. (2020) · IEEE Access · doi:10.1109/access.2020.2989480 · Cited by 27
“For one thing, the maximum of drift distance of VINS-Mono reaches VOLUME 8, 2020 76819 up to 0.7m in the direction of z axes.”
BackgroundMethodInfluentialA Visual Positioning System for Indoor Blind Navigation
Zhang, H., & Ye, C. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196782 · Cited by 32
“Similar to our previous work [32], we select VINS-Mono [28] as the benchmark to evaluate the performance of the DVIO.”
MethodInfluentialNonlinear Observers Design for Vision-Aided Inertial Navigation Systems
Wang, M., Berkane, S., & Tayebi, A. (2021) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2021.3086459 · Cited by 37
“Vision-aided INS is widely used in robotics, for instance, visual-inertial odometry (VIO) and Simultaneous Localization and Mapping (SLAM) [2]–[5].”
MethodOrcVIO: Object residual constrained Visual-Inertial Odometry
Shan, M., Feng, Q., & Atanasov, N. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341660 · Cited by 36
“State of the art VIO approaches work with monocular or stereo cameras [3], often complemented by inertial information [4], [5].”
An Equivariant Filter for Visual Inertial Odometry
van Goor, P., & Mahony, R. E. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561769 · Cited by 34
“Optimisation-based solutions, including ORB-SLAM 3 [3], OKVIS [4] and VINS-Mono [5], treat VI-SLAM as a non-linear least squares problem and optimise over a moving window of data measurements.”
MethodZhou, W., Fan, C., He, X., Hu, X., Ying, F., Wu, X., & Shang, H. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3066844 · Cited by 27
“We mainly refer to the literature for the vision/inertial integrated navigation algorithm, details of relevant parameters can be found in the literature [20].”
Coarse-to-Fine Loosely-Coupled LiDAR-Inertial Odometry for Urban Positioning and Mapping
Zhang, J., Wen, W., Huang, F., Chen, X., & Hsu, L. (2021) · Remote Sensing · doi:10.3390/rs13122371 · Cited by 30
“The major computation load is caused by the point-to-map association, which is similar to the visual reprojection [12], of each LiDAR frame during sliding window optimization.”
BackgroundVisual-Pressure Fusion for Underwater Robot Localization With Online Initialization
Hu, C., Zhu, S., Liang, Y., Mu, Z., & Song, W. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3108584 · Cited by 32
Fast and Accurate Initialization for Monocular Vision/INS/GNSS Integrated System on Land Vehicle
Jin, R., Liu, J., Zhang, H., & Niu, X. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3119982 · Cited by 27
“A. SystemPreliminaries 1) Factor Graph Optimization Model: Numerous modern VIO frameworks have been built, they can be categorized into filter-based [29]–[31] and optimization-based algorithms [5]–[7].”
BackgroundMethodA2DIO: Attention-Driven Deep Inertial Odometry for Pedestrian Localization based on 6D IMU
Wang, Y., Cheng, H., & Meng, M. Q. ‐. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9811714 · Cited by 27
FEJ2: A Consistent Visual-Inertial State Estimator Design
Chen, C., Yang, Y., Geneva, P., & Huang, G. P. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9811831 · Cited by 36
A Tightly Coupled Feature-Based Visual-Inertial Odometry With Stereo Cameras
Yu, L., Qin, J., Wang, S., Wang, Y., & Wang, S. (2022) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2022.3176304 · Cited by 33
“Wealsocompare the performance of our algorithm to other state-of-the-art VIO including OKVIS [23], VI-DSO [10], VINS-FUSION [25], and Basalt [35] on the EuRoC datasets.”
MethodInfluentialPritzl, V., Vrba, M., Štěpán, P., & Saska, M. (2022) · International Conference on Unmanned Aircraft Systems (ICUAS) · doi:10.1109/icuas54217.2022.9836116 · Cited by 36
SLAM-share: visual simultaneous localization and mapping for real-time multi-user augmented reality
Dhakal, A., Ran, X., Wang, Y., Chen, J., & Ramakrishnan, K. K. (2022) · ACM International Conference on emerging Networking EXperiments and Technologies (CoNEXT) · doi:10.1145/3555050.3569142 · Cited by 34
“Here, we focus on tracking and mapping, key components of AR. Finally, many works [8, 34, 36, 40] rely on older frameworks such as ORB-SLAM2 [30] or VINS-Mono [33], which typically perform worse than the state-of-the-art ORB-SLAM3 [16] we use here.”
BackgroundMethodLF-VIO: A Visual-Inertial-Odometry Framework for Large Field-of-View Cameras with Negative Plane
Wang, Z., Yang, K., Shi, H., Li, P., Gao, F., & Wang, K. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981217 · Cited by 32
Self-citationSemanticLoop: Loop Closure With 3D Semantic Graph Matching
Yu, J., & Shen, S. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3229228 · Cited by 28
“[4] T. Qin, P. Li, and S. Shen, “VINS-Mono: A robust and versatile monocular visual-inertial state estimator,” IEEE Trans.”
MethodSelf-citationIndoor Geomagnetic Positioning Using Direction-Aware Multiscale Recurrent Neural Networks
Shu, M., Chen, G., Zhang, Z., & Xu, L. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3227952 · Cited by 29
“Unlike the laborious survey, VIO [44] is employed to obtain the labeled location for geomagnetic sequences using smartphones, which is more convenient and accurate than traditional methods such as interpolation or PDR [16], [45].”
MethodGong, H., Gong, L., Ma, T., Sun, Z., & Li, L. (2023) · Sensors · doi:10.3390/s23094241 · Cited by 28
“Then, visual SLAM began to enter the public vision, and after decades of development, there are some very mature VSLAM algorithms, such as PTAM [4], LSD-SLAM [5], DSO [6], ORB-SLAM2 [7], VINS Mono [8], and RGBD-SLAM [9].”
MethodThoms, A., Earle, G., Charron, N., & Narasimhan, S. (2023) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2023.3265742 · Cited by 29
“For our study, we adopt a graph-based lidar-visual-inertial (LVI) SLAM system [4], which tightly couples the visual-inertial (VI) system from [5] with the lidar-inertial (LI) system from [6].”
MethodStereo Visual Inertial Pose Estimation Based on Feedforward and Feedbacks
Chen, S., Feng, Y., Wen, C., Zou, Y., & Chen, W. (2023) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2023.3272208 · Cited by 31
“Among all monocular vSLAM systems, the scale is handled by an independent process with several alternative solutions, e.g., IMU integrated structure from motion (SFM) [9], predefined object pattern [10], and geometric perspective estimation [11].”
MethodORORA: Outlier-Robust Radar Odometry
Lim, H., Han, K., Shin, G., Kim, G., Hong, S., & Myung, H. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160997 · Cited by 46
“Accordingly, the indirect method takes advantage of being able to apply the techniques that are actively used in the computer vision or LiDAR fields [9], [14], [25], [26].”
MethodLi, Z., & Zhou, A. (2023) · Applied Intelligence · doi:10.1007/s10489-023-04754-7 · Cited by 29
“The selected comparison method includes the handcrafted engineering method (VINS [45]) and the deep learning method (PoseNet [46] and DeepVO [47]).”
MethodTransFusionOdom: Transformer-Based LiDAR-Inertial Fusion Odometry Estimation
Sun, L., Ding, G., Qiu, Y., Yoshiyasu, Y., & Kanehiro, F. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3302401 · Cited by 30
“12 and quantitatively in Table V, which compared with optimization-based VINS-Mono [23] and learning-based fusion approaches, DeepLIO [5], EMA-VIO [1], LeGO-LOAM [26] and so on.”
InfluentialECMD: An Event-Centric Multisensory Driving Dataset for SLAM
Chen, P., Guan, W., Huang, F., Zhong, Y., Wen, W., Hsu, L., & Lu, P. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3339144 · Cited by 40
“As shown in Table IV, we evaluate the performance of VINS-MONO [34], ORB-SLAM3 [35], and ESVIO [36] across Authorized licensed use limited to the terms of the applicable license agreement with IEEE.”
MethodHan, Y., Wang, Q., Yan, C., Feng, Y., Sun, Y., & Li, L. (2024) · Remote Sensing · doi:10.3390/rs16020246 · Cited by 31
A Collaborative Aerial-Ground Robotic System for Fast Exploration
Wang, L., Cheng, D., Gao, F., Cai, F., Guo, J., Lin, M., & Shen, S. (2020) · Springer proceedings in advanced robotics · doi:10.1007/978-3-030-33950-0_6 · Cited by 27
“The Computations including state estimation [10] and exploration planning run on an Intel i7-5500U processor and a Nvidia TX2.”
MethodSelf-citationLoosely-Coupled Ultra-wideband-Aided Scale Correction for Monocular Visual Odometry
Nguyen, T. H., Nguyen, T., Cao, M., & Xie, L. (2020) · Unmanned Systems · doi:10.1142/s2301385020500119 · Cited by 27
RTLIO: Real-Time LiDAR-Inertial Odometry and Mapping for UAVs
Yang, J.-C., Lin, C.-J., You, B.-Y., Yan, Y.-L., & Cheng, T.-H. (2021) · Sensors · doi:10.3390/s21123955 · Cited by 33
“The position, velocity, and orientation states between two body frames b k and b k + 1 can be propagated by integrating IMU measurements ˆ a t and ˆ ω t during t ∈ ( t k , t k + 1 ] in the world frame as where Ω is the same as defined in (3) of [7].”
BackgroundMethodInfluentialGNSS‐stereo‐inertial SLAM for arable farming
Cremona, J., Civera, J., Kofman, E., & Pire, T. (2023) · Journal of Field Robotics · doi:10.1002/rob.22232 · Cited by 33
“A large number of visual-inertial SLAM pipelines have been proposed in the last decade (Mur-Artal & Tard´os, 2017a; Qin et al., 2018; Cam-pos et al., 2021).”
InfluentialR²-GVIO: A Robust, Real-Time GNSS-Visual-Inertial State Estimator in Urban Challenging Environments
Song, J., Li, W., Duan, C., & Zhu, X. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3379755 · Cited by 31
“VINS-Mono [16] is an accurate and robust Lucas–Kanade optical flow monocular-inertial system.”
BackgroundMethodInfluentialDing, S., Zhang, T., Li, Y., Xu, S., & Lei, M. (2024) · Measurement · doi:10.1016/j.measurement.2024.115245 · Cited by 31
Lang, X., Li, L., Wu, C., Zhao, C., Liu, L., Liu, Y., Lv, J., & Zuo, X. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128712 · Cited by 53
“Thus, we propose maintaining a visual sliding window similar to VINS-Mono [50] to compute triangulated SFM points for compensation.”
Asynchronous Multi-Hypothesis Tracking of Features with Event Cameras
Alzugaray, I., & Chli, M. (2019) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2019.00038 · Cited by 26
“However, this does not prevent their application to VO and SLAM system, as such pipelines are usually able to remove erroneous tracks if they do not match the general consensus.”
MethodInfluentialCheng, H., Liu, H., Wang, X., & Liang, B. (2020) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc42975.2020.9283135 · Cited by 33
“Meanwhile, with the development of visual SLAM technology, the advantages of low cost and abundant information of cameras are brought into localization and mapping, such as [2, 3].”
BackgroundSmart Artificial Markers for Accurate Visual Mapping and Localization
Ortiz-Fernandez, L. E., Cabrera-Avila, E. V., da Silva, B. M. F., & Gonçalves, L. M. G. (2021) · Sensors · doi:10.3390/s21020625 · Cited by 28
“Currently, visual odometry has matured to integrate visual SLAM algorithms, as proposed by the current state-of-the-art feature-based visual SLAM algorithms [38–40] or visual-inertial SLAM [15,41–45], which works by fusing visual information with IMU, LIDAR, ToF, GPS or mechanical odometry data.”
MethodOuyang, M., Cao, Z., Guan, P., Li, Z., Zhou, C., & Yu, J. (2021) · IEEE Sensors Letters · doi:10.1109/lsens.2021.3057088 · Cited by 26
“Table1providestheresultsofourmethodwithoutsemantics (VGWO-I)withvisual-inertialmethodVINS-Mono[5],intermsof absoluteposeerror(APE)andrelativeposeerror(RPE).”
BackgroundInfluentialFollowUpAR: enabling follow-up effects in mobile AR applications
Xu, J., Chi, G., Yang, Z., Li, D., Zhang, Q., Ma, Q., & Miao, X. (2021) · International Conference on Mobile Systems, Applications, and Services · doi:10.1145/3458864.3467675 · Cited by 35
“The camera motion tracking module allows the mobile devices to track their own rotation and translation relative to the world by leveraging VO [42] or VIO [37].”
Zhao, Y., Chen, L., Zhang, X., Xu, S., Bu, S., Jiang, H., Han, P., Li, K., & Wan, G. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3090203 · Cited by 32
IMU-Based Estimation of Lower Limb Motion Trajectory With Graph Convolution Network
Chen, Y.-L., Yang, I.-J., Fu, L., Lai, J., Liang, H., & Lu, L. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3115105 · Cited by 28
“To prevent using magnetometers, other sensors, such as cameras [31], [32], laser sensors [33], and UWB [34], were used to optimize the results in several studies, which however increased the complexity of the tracking system.”
MethodCooperative Visual-Inertial Odometry
Zhu, P., Yang, Y., Ren, W., & Huang, G. P. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561674 · Cited by 32
Qing, L., Sun, Y., Wang, L., & Liu, M. (2021) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2021.3105700 · Cited by 28
“As in [38], we aim to perform localization with a minimal visual-inertial sensor suite, commonly used for monocular VIO [7].”
MethodLIO-Vehicle: A Tightly-Coupled Vehicle Dynamics Extension of LiDAR Inertial Odometry
Xiao, H., Han, Y., Zhao, J., Cui, J., Xiong, L., & Yu, Z. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3126336 · Cited by 26
KSF-SLAM: A Key Segmentation Frame Based Semantic SLAM in Dynamic Environments
Zhao, Y., Xiong, Z., Zhou, S., Peng, Z., Campoy, P., & Zhang, L. (2022) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-022-01613-4 · Cited by 29
Zhang, J., Wen, W., Huang, F., Wang, Y., Chen, X., & Hsu, L. (2022) · Applied Sciences · doi:10.3390/app12105193 · Cited by 32
“The control parameter c is set to 1 in our implementation [51].”
BackgroundHigh Definition, Inexpensive, Underwater Mapping
Joshi, B., Xanthidis, M., Rahman, S., & Rekleitis, I. M. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9811695 · Cited by 26
“We evaluate the performance of VINS-Mono [11], ORB-SLAM3[12], SVIn2[10] and OpenVINS[13] based on the RMSE of the ATE as shown in Table II All system are able to track most of the sequences until the end.”
BackgroundMethodInfluentialA Robust and Precise LiDAR-Inertial-GPS Odometry and Mapping Method for Large-Scale Environment
Wu, Y., & Zhao, J. (2022) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2022.3170416 · Cited by 28
“To avoid the map being too dense and improve the computational efficiency, the global map is constructed by using keyframes and their features with reference to the visual SLAM system [27].”
MethodOnline Kinematic Calibration for Legged Robots
Yang, S., Choset, H., & Manchester, Z. R. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3186501 · Cited by 28
“We also show doing online calibration in an optimization-based sliding-window state estimator [11] is possible.”
MethodRobust Real-Time AUV Self-Localization Based on Stereo Vision-Inertia
Wang, Y., Gu, D., Ma, X., Wang, J., & Wang, H. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3241634 · Cited by 26
“Most vision-based localization algorithms [14], [15], [16], [17] were used to estimate the pose of”
MethodGIVE: A Tightly Coupled RTK-Inertial–Visual State Estimator for Robust and Precise Positioning
Wang, X., Li, X., Chang, H., Li, S., Shen, Z., & Zhou, Y. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3282296 · Cited by 37
“The corresponding Jacobian matrix on the IMU error states can refer to [31].”
BackgroundMethodInfluentialVIMOT: A Tightly Coupled Estimator for Stereo Visual-Inertial Navigation and Multiobject Tracking
Feng, S., Li, X., Xia, C., Liao, J., Zhou, Y., Li, S., & Hua, X. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3291011 · Cited by 31
“7(a) and (b) shows, the RANSAC method performs poorly in dynamic environments, whereas the proposed cross-frame methods can effectively distinguish their dynamic features, which is attributed to the accurate fundamental matrix provided by VINS.”
BackgroundInfluentialJoint Beam Management and SLAM for mmWave Communication Systems
Que, H., Yang, J., Wen, C.-K., Xia, S., Li, X., & Jin, S. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3294954 · Cited by 26
“SLAM originally emerged from the field of robotics [14], where the robots are required to locate themselves and map their environment through sensor networks, such as inertial measurement unit (IMU), camera [15], or light detection and ranging (LiDAR) [16].”
BackgroundAutonomous Dam Surveillance Robot System Based on Multi-Sensor Fusion
Zhang, C., Zhan, Q., Wang, Q., Wu, H., He, T., & An, Y. (2020) · Sensors · doi:10.3390/s20041097 · Cited by 26
“Visual odometer (VO) is another hot topic in this area [8,9].”
BackgroundLOCUS: A Multi-Sensor Lidar-Centric Solution for High-Precision Odometry and 3D Mapping in Real-TimePreprint
Palieri, M., Morrell, B. J., Thakur, A., Ebadi, K., Nash, J., Chatterjee, A., Kanellakis, C., Carlone, L., Guaragnella, C., & Agha–mohammadi, A. (2021) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 26
Deep Learning-Based Stereopsis and Monocular Depth Estimation Techniques: A Review
Lahiri, S., Ren, J., & Lin, X. (2024) · Vehicles · doi:10.3390/vehicles6010013 · Cited by 36
“The method of VINS-Mono (Monocular Visual-Inertial System) [129] has been adopted.”
MethodZeng, D., Liu, X., Huang, K., & Liu, J. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3398491 · Cited by 27
“Refer to [6] for further details.”
Mac, T. T., Lin, C., Huan, N. G., LUONG, D. N., Hoang, P. C., & Hai, H. H. (2021) · Acta Polytechnica Hungarica · doi:10.12700/aph.18.6.2021.6.11 · Cited by 28
“Other approaches such as DSO (Direct Sparse Odometry) [12], VINS-Mono (Monocular Visual-Inertial System) [13] are introduced to save computing resources in tracking and matching.”
MethodPanoramic Visual-Inertial SLAM Tightly Coupled with a Wheel Encoder
Jiang, F., Chen, J., & Ji, S. (2021) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2021.10.006 · Cited by 29
Li, S., Zhang, J., Zhao, K., Zhang, Y., Sun, Z., & Xia, Y. (2021) · International Journal of Robust and Nonlinear Control · doi:10.1002/rnc.5926 · Cited by 25
LILO: A Novel Lidar–IMU SLAM System With Loop Optimization
Zhang, Y. (2021) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2021.3135234 · Cited by 27
Zhang, T., Liu, C., Li, J., Pang, M., & Wang, M. (2022) · Drones · doi:10.3390/drones6010023 · Cited by 26
x-RIO: Radar Inertial Odometry with Multiple Radar Sensors and Yaw Aiding
Doer, C., & Trommer, G. F. (2021) · Gyroscopy and Navigation · doi:10.1134/s2075108721040039 · Cited by 25
“Visual Inertial Odometry (VIO) has been successfully demonstrated for navigation of UAS [1–3].”
BackgroundMethodInfluentialThe Deep Convolutional Neural Network Role in the Autonomous Navigation of Mobile Robots (SROBO)
Esfahlani, S. S., Sanaei, A., Ghorabian, M., & Shirvani, H. (2022) · Remote Sensing · doi:10.3390/rs14143324 · Cited by 31
PLI-VINS: Visual-Inertial SLAM Based on Point-Line Feature Fusion in Indoor Environment
Zhao, Z., Song, T., Xing, B., Yu, L., & Wang, Z. (2022) · Sensors · doi:10.3390/s22145457 · Cited by 29
Saha, A., Dhara, B. C., Umer, S., Kulakov, Y., Alanazi, J. M., & AlZubi, A. A. (2022) · Sensors · doi:10.3390/s22176537 · Cited by 31
“VINS-MONO [30] is one popular SoA localization system that uses monocular images and Inertial Measurement Unit (IMU) measurements to estimate a robot poses in the fixed world coordinate frame w.”
BackgroundMethodInfluentialNg, H., Hsu, L., Lee, M. J. L., Feng, J., Naeimi, T., Beheshti, M., & Rizzo, J. (2022) · Sensors · doi:10.3390/s22176533 · Cited by 25
“Therefore, research indicates tightly coupled VO with INS improves positioning performance [12].”
BackgroundMonocular Visual-Inertial Odometry for Agricultural Environments
Song, K., Li, J., Qiu, R., & Yang, G. (2022) · IEEE Access · doi:10.1109/access.2022.3209186 · Cited by 25
“Using the IMU pre-integration method, the IMU sensor can solve the problem of tracking failure and low precision when the monocular camera moves into a complex environment [23].”
BackgroundMethodInfluentialRobust Depth-Aided RGBD-Inertial Odometry for Indoor Localization
Zhao, X., Li, Q., Wang, C., Dou, H., & Liu, B. (2023) · Measurement · doi:10.1016/j.measurement.2023.112487 · Cited by 26
ARD‐VO: Agricultural robot data set of vineyards and olive groves
Crocetti, F., Bellocchio, E., Dionigi, A., Felicioni, S., Costante, G., Fravolini, M. L., & Valigi, P. (2023) · Journal of Field Robotics · doi:10.1002/rob.22179 · Cited by 30
“(a) FLOAM, (b) LeGO‐LOAM, (c) DSO, (d) Open‐VINS, (e) VINS‐Mono, (f) ORB‐SLAM Mono, and (g) ORB‐SLAM Stereo.”
InfluentialSong, Z., Zhang, X., Li, T., Zhang, S., Wang, Y., & Yuan, J. (2023) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2023.3277031 · Cited by 25
“We compare IR-VIO with ROVIO [24], OKVIS [25], VINS-Mono [8], R-VIO [26], and R-VIO2 [27], which are state-of-the-art monocular VIO methods.”
BackgroundMethodInfluentialAdaptive Keyframe Generation based LiDAR Inertial Odometry for Complex Underground Environments
Kim, B., Jung, C., Shim, D. H., & Agha–mohammadi, A. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10161207 · Cited by 33
“Due to its small and lightweight hardware characteristics, vision-based state estimation algorithms [1]–[4] using a stereo or monocular camera have a great advantage in the field of unmanned aerial vehicles.”
BackgroundDistributed optimization of networked marine surface vehicles: A fixed-time estimator-based approach
Chen, Q., Ge, M., Liang, C., Gu, Z.-W., & Liu, J. (2023) · Ocean Engineering · doi:10.1016/j.oceaneng.2023.115275 · Cited by 25
Real-time GAN-based image enhancement for robust underwater monocular SLAM
Zheng, Z., Xin, Z., Yu, Z., & Yeung, S.-K. (2023) · Frontiers in Marine Science · doi:10.3389/fmars.2023.1161399 · Cited by 33
Wang, R., Wang, K., Song, W., & Fu, M. (2023) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2023.3312627 · Cited by 25
“In this article, we follow the visual-inertial SLAM algorithm in [30].”
MethodOu, Y., Fan, J., Zhou, C., Cheng, L., & Tan, M. H. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2023.3342899 · Cited by 26
“In addition, Br ¨a uer-Burchardt et al. [21] attempted to estimate the robot motion state based on VINS-Mono [20] using a monocular and inertial measurement unit (IMU) [21].”
MethodQuadtree-Accelerated Real-Time Monocular Dense Mapping
Wang, K., Ding, W., & Shen, S. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8594101 · Cited by 26
“Our dense mapping system runs on TX1 and the other components including VINS [3] and planning run on the i7 computer.”
MethodSelf-citationTightly-coupled Data Fusion of VINS and Odometer Based on Wheel Slip Estimation
Dang, Z., Wang, T., & Pang, F. (2018) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2018.8665337 · Cited by 25
“The tightly-coupled nonlinear optimization-based state estimator [23] employed in our implementation maintains a sliding window of 10 poses.”
MethodTowards SLAM-Based Outdoor Localization using Poor GPS and 2.5D Building Models
Liu, R., Zhang, J., Chen, S., & Arth, C. (2019) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2019.00016 · Cited by 26
“[29, 32, 37] are sophisticated and popular methods about fusing IMU and vision in recent years.”
MethodActive Perception for Outdoor Localisation with an Omnidirectional Camera
Jayasuriya, M., Ranasinghe, R., & Dissanayake, G. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9340974 · Cited by 26
“Feature based approaches that first extract low level handcrafted features such as SIFT, SURF or ORB features in order to carry out pose estimation, such as ORB-SLAM [6], [9], VINS [7], Kimera [10] and RTAB [8] are noteworthy state of the art contributions.”
MethodBai, X., Wen, W., & Hsu, L. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3126010 · Cited by 28
“To further study the performance of the VINS in the challenging outdoor urban canyons, we evaluated and analyzed the VINS-Mono [9] based on the datasets collected in urban canyons of Hong Kong.”
BackgroundMethodInfluentialInvariant Smoother for Legged Robot State Estimation With Dynamic Contact Event Information
Yoon, Z., Kim, J.-H., & Park, H.-W. (2023) · IEEE Transactions on Robotics · doi:10.1109/tro.2023.3328202 · Cited by 44
“…algorithms preserve only a few latest states and measurements by marginalizing out the oldest, where the fixed-lag smoother keeps its states as many as its window size [13], [14], [15], [16], [17], [18], and [19], whereas the filter holds only the two latest states [20], [21], [22], [23], and [24].”
BackgroundWang, X., Luo, H., Wang, Z., Zheng, J. Y., & Bai, X. P. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102363 · Cited by 24
Jiang, H., Qian, R., Du, L., Pu, J., & Feng, J. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3382770 · Cited by 28
“Depending on the type of sensor input used, it can be divided into visual SLAM (V-SLAM) [2], [3], [4], [5], [6], [7], visual-inertial SLAM (VI-SLAM) [8], [9], [10], [11], and LiDAR SLAM (L-SLAM) [12], [13].”
Unlocking aerobatic potential of quadcopters: Autonomous freestyle flight generation and execution
Wang, M., Wang, Q., Wang, Z., Gao, Y., Wang, J., Cui, C., Li, Y., Ding, Z., Wang, K., Xu, C., et al. (2025) · Science Robotics · doi:10.1126/scirobotics.adp9905 · Cited by 24
GS-LIVO: Real-Time LiDAR, Inertial, and Visual Multisensor Fused Odometry With Gaussian Mapping
Hong, S., Zheng, C., Shen, Y., Li, C., Zhang, F., Qin, T., & Shen, S. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3582809 · Cited by 36
“These forms, often integrated with feature-based or direct methods, support efficient, real-time operation across platforms such as aerial robotics and mobile robots [2], [3], [4], [5], [7], [22], [23].”
Self-citationMeng, Z., Ji, J., Liu, L., Liu, S., Sun, Z., Xiao, Q., & Yang, Z. (2025) · Case Studies on Transport Policy · doi:10.1016/j.cstp.2025.101629 · Cited by 27
Robust RGB-D SLAM Using Point and Line Features for Low Textured Scene
Zou, Y., Eldemiry, A., Li, Y., & Chen, W. (2020) · Sensors · doi:10.3390/s20174984 · Cited by 25
“The candidate keyframe has the highest score.”
Multi‐sensor fusion SLAM approach for the mobile robot with a bio‐inspired polarised skylight sensor
Du, T., Zeng, Y., Yang, J., Tian, C., & Bai, P. F. (2020) · IET Radar Sonar & Navigation · doi:10.1049/iet-rsn.2020.0260 · Cited by 25
Metadata
- Authors
- Qin, T., Li, P., & Shen, S.
- Affiliations
- Hong Kong University of Science and Technology (HK)
- Venue
- IEEE Transactions on Robotics
- Published
- 2018-08
- Volume
- 34
- Issue
- 4
- Pages
- 1004-1020
- ISSN
- 1552-3098 (ISSN-L)
- 1941-0468
- OpenAlex
- W2745859992
- Cited by
- 4,669
- References
- 53
- Citations by year
- 2026: 575 · 2025: 856 · 2024: 789 · 2023: 729 · 2022: 571 · 2021: 469 · 2020: 357 · 2019: 248 · 2018: 73
- FWCI
- 233.33
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- IEEE Transactions on Robotics (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Hong Kong Research Grants Council Early Career Scheme (26201616)
- HKUST Proof-of-Concept (PCF.009.16/17)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Engineering › Aerospace Engineering › Inertial Sensor and Navigation
- Physical Sciences › Engineering › Aerospace Engineering › Aerospace Engineering and Control Systems
- Keywords
- loop detection, relocalization, pose graph optimization, autonomous flight
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.